O SlideShare utiliza cookies para otimizar a funcionalidade e o desempenho do site, assim como para apresentar publicidade mais relevante aos nossos usuários. Se você continuar a navegar o site, você aceita o uso de cookies. Leia nosso Contrato do Usuário e nossa Política de Privacidade.

O SlideShare utiliza cookies para otimizar a funcionalidade e o desempenho do site, assim como para apresentar publicidade mais relevante aos nossos usuários. Se você continuar a utilizar o site, você aceita o uso de cookies. Leia nossa Política de Privacidade e nosso Contrato do Usuário para obter mais detalhes.

O slideshow foi denunciado.

Gostou da apresentação? Compartilhe-a!

- Large Graph Mining – Patterns, tool... by BigMine 6097 views
- Processing Reachability Queries wit... by BigMine 3646 views
- Challenging Problems for Scalable M... by BigMine 4485 views
- Netflix Case Study by Kikuyu Daniels 178825 views
- Netflix Case Study by Julien Guitton 46651 views
- The Netflix Way to deal with Big Da... by Monal Daxini 2827 views

5.717 visualizações

Publicada em

In this talk I will discuss the different approaches we follow to deal with these large streams of data in order to extract information for personalizing our service. I will describe some of the machine learning models used, as well as the architectures that allow us to combine complex offline batch processes with real-time data streams.

Sem downloads

Visualizações totais

5.717

No SlideShare

0

A partir de incorporações

0

Número de incorporações

2.522

Compartilhamentos

0

Downloads

197

Comentários

0

Gostaram

14

Nenhuma incorporação

Nenhuma nota no slide

- 1. Big & Personal: the data and the models behind Netflix recommendations
- 2. Outline 1. The Netflix Prize & the Recommendation Problem 2. Anatomy of Netflix Personalization 3. Data & Models 4. More data or better Models?
- 3. What we were interested in: ■ High quality recommendations Proxy question: ■ Accuracy in predicted rating ■ Improve by 10% = $1million! ● Top 2 algorithms still in production Results SVD RBM
- 4. What about the final prize ensembles? ■ Our offline studies showed they were too computationally intensive to scale ■ Expected improvement not worth the engineering effort ■ Plus…. Focus had already shifted to other issues that had more impact than rating prediction.
- 5. Change of focus 2006 2013
- 6. Anatomy of Netflix Personalization Everything is a Recommendation
- 7. Everything is personalized Note: Recommendations are per household, not individual user Ranking
- 8. Top 10 Personalization awareness Diversity DadAll SonDaughterDad&Mom MomAll Daughter MomAll?
- 9. Support for Recommendations Social Support
- 10. Social Recommendations
- 11. Genre rows ■ Personalized genre rows focus on user interest ■ Also provide context and “evidence” ■ Important for member satisfaction – moving personalized rows to top on devices increased retention ■ How are they generated? ■ Implicit: based on user’s recent plays, ratings, & other interactions ■ Explicit taste preferences ■ Hybrid:combine the above ■ Also take into account: ■ Freshness - has this been shown before? ■ Diversity– avoid repeating tags and genres, limit number of TV genres, etc.
- 12. Genres - personalization
- 13. ■ Displayed in many different contexts ■ In response to user actions/context (search, queue add…) ■ More like… rows Similars
- 14. Data & Models
- 15. Big Data @Netflix ■ Almost 40M subscribers ■ Ratings: 4M/day ■ Searches: 3M/day ■ Plays: 30M/day ■ 2B hours streamed in Q4 2011 ■ 1B hours in June 2012 ■ > 4B hours in Q1 2013 Member Behavior Geo-informationTime Impressions Device Info Metadata Social
- 16. Smart Models ■ Logistic/linear regression ■ Elastic nets ■ SVD and other MF models ■ Factorization Machines ■ Restricted Boltzmann Machines ■ Markov Chains ■ Different clustering approaches ■ LDA ■ Association Rules ■ Gradient Boosted Decision Trees/Random Forests ■ …
- 17. SVD X[n x m] = U[n x r] S [ r x r] (V[m x r] )T ■ X: m x n matrix (e.g., m users, n videos) ■ U: m x r matrix (m users, r factors) ■ S: r x r diagonal matrix (strength of each ‘factor’) (r: rank of the matrix) ■ V: r x n matrix (n videos, r factor)
- 18. SVD for Rating Prediction ■ User factor vectors and item-factors vector ■ Baseline (bias) (user & item deviation from average) ■ Predict rating as ■ SVD++ (Koren et. Al) asymmetric variation w. implicit feedback ■ Where ■ are three item factor vectors ■ Users are not parametrized, but rather represented by: ■ R(u): items rated by user u ■ N(u): items for which the user has given implicit preference (e.g. rated vs. not rated)
- 19. Simon Funk’s SVD ■ One of the most interesting findings during the Netflix Prize came out of a blog post ■ Incremental, iterative, and approximate way to compute the SVD using gradient descent
- 20. Restricted Boltzmann Machines ■ Restrict the connectivity in ANN to make learning easier. ■ Only one layer of hidden units. ■ Although multiple layers are possible ■ No connections between hidden units. ■ Hidden units are independent given the visible states.. ■ RBMs can be stacked to form Deep Belief Networks (DBN) – 4th generation of ANNs hidden i j visible
- 21. RBM for the Netflix Prize
- 22. Ranking Key algorithm, sorts titles in most contexts
- 23. Ranking ■ Ranking = Scoring + Sorting + Filtering bags of movies for presentation to a user ■ Goal: Find the best possible ordering of a set of videos for a user within a specific context in real-time ■ Objective: maximize consumption ■ Aspirations: Played & “enjoyed” titles have best score ■ Akin to CTR forecast for ads/search results ■ Factors ■ Accuracy ■ Novelty ■ Diversity ■ Freshness ■ Scalability ■ …
- 24. Example: Two features, linear model
- 25. Example: Two features, linear model
- 26. Ranking
- 27. Ranking
- 28. Ranking Novelty Diversity Freshness Accuracy Scalability
- 29. Learning to rank ■ Machine learning problem: goal is to construct ranking model from training data ■ Training data can have partial order or binary judgments (relevant/not relevant). ■ Resulting order of the items typically induced from a numerical score ■ Learning to rank is a key element for personalization ■ You can treat the problem as a standard supervised classification problem
- 30. Learning to Rank Approaches 1. Pointwise ■ Ranking function minimizes loss function defined on individual relevance judgment ■ Ranking score based on regression or classification ■ Ordinal regression, Logistic regression, SVM, GBDT, … 2. Pairwise ■ Loss function is defined on pair-wise preferences ■ Goal: minimize number of inversions in ranking ■ Ranking problem is then transformed into the binary classification problem ■ RankSVM, RankBoost, RankNet, FRank…
- 31. Learning to rank - metrics ■ Quality of ranking measured using metrics as ■ Normalized Discounted Cumulative Gain ■ Mean Reciprocal Rank (MRR) ■ Fraction of Concordant Pairs (FCP) ■ Others… ■ But, it is hard to optimize machine-learned models directly on these measures (they are not differentiable) ■ Recent research on models that directly optimize ranking measures
- 32. Learning to Rank Approaches 3. Listwise a. Indirect Loss Function ■ RankCosine: similarity between ranking list and ground truth as loss function ■ ListNet: KL-divergence as loss function by defining a probability distribution ■ Problem: optimization of listwise loss function may not optimize IR metrics b. Directly optimizing IR measures (difficult since they are not differentiable) ■ Directly optimize IR measures through Genetic Programming or Simulated Annealing ■ Gradient descent on smoothed version of objective function (e.g. CLiMF at Recsys 2012 or TFMAP at SIGIR 2012) ■ SVM-MAP relaxes the MAP metric by adding it to the SVM constraints ■ AdaRank uses boosting to optimize NDCG
- 33. Other research questions we are interested on ● Row selection ○ How to select and rank lists of “related” items imposing inter- group diversity, avoiding duplicates... ● Diversity ○ Can we increase diversity while preserving relevance in a way that we optimize user response? ● Similarity ○ How to compute optimal and personalized similarity between items by using different data that can range from play histories to item metadata ● Context-aware recommendations ● Mood and session intent inference ● ...
- 34. More data or better models?
- 35. More data or better models? Really? Anand Rajaraman: Stanford & Senior VP at Walmart Global eCommerce (former Kosmix)
- 36. Sometimes, it’s not about more data More data or better models?
- 37. [Banko and Brill, 2001] Norvig: “Google does not have better Algorithms, only more Data” Many features/ low-bias models More data or better models?
- 38. More data or better models? Sometimes, it’s not about more data
- 39. X More data or better models?
- 40. Data without a sound approach = noise
- 41. Conclusions
- 42. The Personalization Problem ■ The Netflix Prize simplified the recommendation problem to predicting ratings ■ But… ■ User ratings are only one of the many data inputs we have ■ Rating predictions are only part of our solution ■ Other algorithms such as ranking or similarity are very important ■ We can reformulate the recommendation problem ■ Function to optimize: probability a user chooses something and enjoys it enough to come back to the service
- 43. More data + Better models + More accurate metrics + Better approaches & architectures Lots of room for improvement!
- 44. Thanks! Xavier Amatriain (@xamat) xavier@netflix.com We’re hiring!

Nenhum painel de recortes público que contém este slide

Parece que você já adicionou este slide ao painel

Criar painel de recortes

Seja o primeiro a comentar